metadata
base_model: facebook/dino-vitb16
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: DINO Model (model_idx_0892)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | DINO |
| Split | train |
| Base Model | facebook/dino-vitb16 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 5e-05 |
| LR Scheduler | constant |
| Epochs | 3 |
| Max Train Steps | 999 |
| Batch Size | 64 |
| Weight Decay | 0.03 |
| Seed | 892 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9819 |
| Val Accuracy | 0.8837 |
| Test Accuracy | 0.8810 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
pear, plain, hamster, seal, tiger, crocodile, snail, telephone, tank, woman, bridge, cloud, lobster, rocket, couch, bottle, poppy, dinosaur, cup, raccoon, beaver, rabbit, dolphin, baby, elephant, aquarium_fish, forest, lawn_mower, oak_tree, skyscraper, lamp, crab, mouse, maple_tree, skunk, boy, bee, sweet_pepper, chimpanzee, pickup_truck, man, motorcycle, possum, leopard, bed, squirrel, beetle, chair, plate, bear